Data-driven prognostic method based on self-supervised learning approaches for fault detection
- PDF / 517,092 Bytes
- 9 Pages / 595.276 x 790.866 pts Page_size
- 61 Downloads / 302 Views
Data-driven prognostic method based on self-supervised learning approaches for fault detection Tian Wang1
· Meina Qiao1 · Mengyi Zhang2 · Yi Yang3 · Hichem Snoussi4
Received: 6 January 2018 / Accepted: 15 June 2018 © Springer Science+Business Media, LLC, part of Springer Nature 2018
Abstract As a part of prognostics and health management (PHM), fault detection has been used in many fields to improve the reliability of the system and reduce the manufacturing costs. Due to the complexity of the system and the richness of the sensors, fault detection still faces some challenges. In this paper, we propose a data-driven method in a self-supervised manner, which is different from previous prognostic methods. In our algorithm, we first extract feature indices of each batch and concatenate them into one feature vector. Then the principal components are extracted by Kernel PCA. Finally, the fault is detected by the reconstruction error in the feature space. Samples with high reconstruction error are identified as faulty. To demonstrate the effectiveness of the proposed algorithm, we evaluate our algorithm on a benchmark dataset for fault detection, and the results show that our algorithm outperforms other fault detection methods. Keywords Fault detection · Self-supervised · Kernel PCA · Prognostics and health management
Introduction The development of smart manufacturing calls for efficient and effective production. With the help of advanced machines, such as the powerful industrial robot, the collaboration of different types of devices by the internet of things and cyber-physical systems (Xia and Xi 2017), the production efficiency of the industry is highly improved. However, the product quality inspection meets severe situations and challenges at the same time (Aminzadeh and Kurfess 2018). The traditional solution for fault detection is the random inspection for a batch of production by the human. With the high technical examination equipment, the
B
Tian Wang [email protected] Mengyi Zhang [email protected]
1
School of Automation Science and Electrical Engineering, Beihang University, Beijing 100191, China
2
College of Electrical Engineering and Control Science, Nanjing Tech University, Nanjing 211800, China
3
School of Electrical Engineering and Automation, Henan Polytechnic University, Jiaozuo 454000, China
4
Institute Charles Delaunay-LM2S-UMR STMR 6279 CNRS, University of Technology of Troyes, 10010 Troyes, France
technicians in the inspection process usually cannot catch out all the fault situation due to the inefficiency of people’s longtime high-intensity work. Moreover, in the sampled strategy, the quality of all the products cannot be guaranteed. With the development of sensors, different types of sensors can monitor the environment and variable value of the machines incessantly. A potential method for product quality inspection can be adopted by analyzing the status of the monitoring data (Lin et al. 2018). If the situation of the production can be interpreted in time, the proper fault dete
Data Loading...
